/*
 *  linux/arch/arm/kernel/head.S
 *
 *  Copyright (C) 1994-2002 Russell King
 *  Copyright (c) 2003 ARM Limited
 *  All Rights Reserved
 *
 * This program is free software; you can redistribute it and/or modify
 * it under the terms of the GNU General Public License version 2 as
 * published by the Free Software Foundation.
 *
 *  Kernel startup code for all 32-bit CPUs
 */
#include <linux/config.h>
#include <linux/linkage.h>
#include <linux/init.h>

#include <asm/assembler.h>
#include <asm/domain.h>
#include <asm/procinfo.h>
#include <asm/ptrace.h>
#include <asm/asm-offsets.h>
#include <asm/memory.h>
#include <asm/thread_info.h>
#include <asm/system.h>

#define PROCINFO_MMUFLAGS	8
#define PROCINFO_INITFUNC	12

#define MACHINFO_TYPE		0
#define MACHINFO_PHYSIO		4
#define MACHINFO_PGOFFIO	8
#define MACHINFO_NAME		12

#define KERNEL_RAM_ADDR	(PAGE_OFFSET + TEXT_OFFSET)

/*
 * swapper_pg_dir is the virtual address of the initial page table.
 * We place the page tables 16K below KERNEL_RAM_ADDR.  Therefore, we must
 * make sure that KERNEL_RAM_ADDR is correctly set.  Currently, we expect
 * the least significant 16 bits to be 0x8000, but we could probably
 * relax this restriction to KERNEL_RAM_ADDR >= PAGE_OFFSET + 0x4000.
 */
#if (KERNEL_RAM_ADDR & 0xffff) != 0x8000
#error KERNEL_RAM_ADDR must start at 0xXXXX8000
#endif

	.globl	swapper_pg_dir
	.equ	swapper_pg_dir, KERNEL_RAM_ADDR - 0x4000

	.macro	pgtbl, rd
	ldr	\rd, =(__virt_to_phys(KERNEL_RAM_ADDR - 0x4000))
	.endm

#ifdef CONFIG_XIP_KERNEL
#define TEXTADDR  XIP_VIRT_ADDR(CONFIG_XIP_PHYS_ADDR)
#else
#define TEXTADDR  KERNEL_RAM_ADDR
#endif

/*
 * Kernel startup entry point.
 * ---------------------------
 *
 * This is normally called from the decompressor code.  The requirements
 * are: MMU = off, D-cache = off, I-cache = dont care, r0 = 0,
 * r1 = machine nr.
 *
 * This code is mostly position independent, so if you link the kernel at
 * 0xc0008000, you call this at __pa(0xc0008000).
 *
 * See linux/arch/arm/tools/mach-types for the complete list of machine
 * numbers for r1.
 *
 * We're trying to keep crap to a minimum; DO NOT add any machine specific
 * crap here - that's what the boot loader (or in extreme, well justified
 * circumstances, zImage) is for.
 */
	__INIT
	.type	stext, %function
ENTRY(stext)
	msr	cpsr_c, #PSR_F_BIT | PSR_I_BIT | MODE_SVC @ ensure svc mode
						@ and irqs disabled
	mrc	p15, 0, r9, c0, c0		@ get processor id
	bl	__lookup_processor_type		@ r5=procinfo r9=cpuid
	movs	r10, r5				@ invalid processor (r5=0)?
	beq	__error_p			@ yes, error 'p'
	bl	__lookup_machine_type		@ r5=machinfo
	movs	r8, r5				@ invalid machine (r5=0)?
	beq	__error_a			@ yes, error 'a'
	bl	__create_page_tables

	/*
	 * The following calls CPU specific code in a position independent
	 * manner.  See arch/arm/mm/proc-*.S for details.  r10 = base of
	 * xxx_proc_info structure selected by __lookup_machine_type
	 * above.  On return, the CPU will be ready for the MMU to be
	 * turned on, and r0 will hold the CPU control register value.
	 */
	ldr	r13, __switch_data		@ address to jump to after
						@ mmu has been enabled
	adr	lr, __enable_mmu		@ return (PIC) address
	add	pc, r10, #PROCINFO_INITFUNC

#if defined(CONFIG_SMP)
	.type   secondary_startup, #function
ENTRY(secondary_startup)
	/*
	 * Common entry point for secondary CPUs.
	 *
	 * Ensure that we're in SVC mode, and IRQs are disabled.  Lookup
	 * the processor type - there is no need to check the machine type
	 * as it has already been validated by the primary processor.
	 */
	msr	cpsr_c, #PSR_F_BIT | PSR_I_BIT | MODE_SVC
	mrc	p15, 0, r9, c0, c0		@ get processor id
	bl	__lookup_processor_type
	movs	r10, r5				@ invalid processor?
	moveq	r0, #'p'			@ yes, error 'p'
	beq	__error

	/*
	 * Use the page tables supplied from  __cpu_up.
	 */
	adr	r4, __secondary_data
	ldmia	r4, {r5, r6, r13}		@ address to jump to after
	sub	r4, r4, r5			@ mmu has been enabled
	ldr	r4, [r6, r4]			@ get secondary_data.pgdir
	adr	lr, __enable_mmu		@ return address
	add	pc, r10, #12			@ initialise processor
						@ (return control reg)

	/*
	 * r6  = &secondary_data
	 */
ENTRY(__secondary_switched)
	ldr	sp, [r6, #4]			@ get secondary_data.stack
	mov	fp, #0
	b	secondary_start_kernel

	.type	__secondary_data, %object
__secondary_data:
	.long	.
	.long	secondary_data
	.long	__secondary_switched
#endif /* defined(CONFIG_SMP) */


/*
 * Setup common bits before finally enabling the MMU.  Essentially
 * this is just loading the page table pointer and domain access
 * registers.
 */
	.type	__enable_mmu, %function
__enable_mmu:
#ifdef CONFIG_ALIGNMENT_TRAP
	orr	r0, r0, #CR_A
#else
	bic	r0, r0, #CR_A
#endif
#ifdef CONFIG_CPU_DCACHE_DISABLE
	bic	r0, r0, #CR_C
#endif
#ifdef CONFIG_CPU_BPREDICT_DISABLE
	bic	r0, r0, #CR_Z
#endif
#ifdef CONFIG_CPU_ICACHE_DISABLE
	bic	r0, r0, #CR_I
#endif
	mov	r5, #(domain_val(DOMAIN_USER, DOMAIN_MANAGER) | \
		      domain_val(DOMAIN_KERNEL, DOMAIN_MANAGER) | \
		      domain_val(DOMAIN_TABLE, DOMAIN_MANAGER) | \
		      domain_val(DOMAIN_IO, DOMAIN_CLIENT))
	mcr	p15, 0, r5, c3, c0, 0		@ load domain access register
	mcr	p15, 0, r4, c2, c0, 0		@ load page table pointer
	b	__turn_mmu_on

/*
 * Enable the MMU.  This completely changes the structure of the visible
 * memory space.  You will not be able to trace execution through this.
 * If you have an enquiry about this, *please* check the linux-arm-kernel
 * mailing list archives BEFORE sending another post to the list.
 *
 *  r0  = cp#15 control register
 *  r13 = *virtual* address to jump to upon completion
 *
 * other registers depend on the function called upon completion
 */
	.align	5
	.type	__turn_mmu_on, %function
__turn_mmu_on:
	mov	r0, r0
	mcr	p15, 0, r0, c1, c0, 0		@ write control reg
	mrc	p15, 0, r3, c0, c0, 0		@ read id reg
	mov	r3, r3
	mov	r3, r3
	mov	pc, r13


/*
 * Setup the initial page tables.  We only setup the barest
 * amount which are required to get the kernel running, which
 * generally means mapping in the kernel code.
 *
 * r8  = machinfo
 * r9  = cpuid
 * r10 = procinfo
 *
 * Returns:
 *  r0, r3, r6, r7 corrupted
 *  r4 = physical page table address
 */
	.type	__create_page_tables, %function
__create_page_tables:
	pgtbl	r4				@ page table address

	/*
	 * Clear the 16K level 1 swapper page table
	 */
	mov	r0, r4
	mov	r3, #0
	add	r6, r0, #0x4000
1:	str	r3, [r0], #4
	str	r3, [r0], #4
	str	r3, [r0], #4
	str	r3, [r0], #4
	teq	r0, r6
	bne	1b

	ldr	r7, [r10, #PROCINFO_MMUFLAGS]	@ mmuflags

	/*
	 * Create identity mapping for first MB of kernel to
	 * cater for the MMU enable.  This identity mapping
	 * will be removed by paging_init().  We use our current program
	 * counter to determine corresponding section base address.
	 */
	mov	r6, pc, lsr #20			@ start of kernel section
	orr	r3, r7, r6, lsl #20		@ flags + kernel base
	str	r3, [r4, r6, lsl #2]		@ identity mapping

	/*
	 * Now setup the pagetables for our kernel direct
	 * mapped region.  We round TEXTADDR down to the
	 * nearest megabyte boundary.  It is assumed that
	 * the kernel fits within 4 contigous 1MB sections.
	 */
	add	r0, r4,  #(TEXTADDR & 0xff000000) >> 18	@ start of kernel
	str	r3, [r0, #(TEXTADDR & 0x00f00000) >> 18]!
	add	r3, r3, #1 << 20
	str	r3, [r0, #4]!			@ KERNEL + 1MB
	add	r3, r3, #1 << 20
	str	r3, [r0, #4]!			@ KERNEL + 2MB
	add	r3, r3, #1 << 20
	str	r3, [r0, #4]			@ KERNEL + 3MB

	/*
	 * Then map first 1MB of ram in case it contains our boot params.
	 */
	add	r0, r4, #PAGE_OFFSET >> 18
	orr	r6, r7, #PHYS_OFFSET
	str	r6, [r0]

#ifdef CONFIG_XIP_KERNEL
	/*
	 * Map some ram to cover our .data and .bss areas.
	 * Mapping 3MB should be plenty.
	 */
	sub	r3, r4, #PHYS_OFFSET
	mov	r3, r3, lsr #20
	add	r0, r0, r3, lsl #2
	add	r6, r6, r3, lsl #20
	str	r6, [r0], #4
	add	r6, r6, #(1 << 20)
	str	r6, [r0], #4
	add	r6, r6, #(1 << 20)
	str	r6, [r0]
#endif

#ifdef CONFIG_DEBUG_LL
	bic	r7, r7, #0x0c			@ turn off cacheable
						@ and bufferable bits
	/*
	 * Map in IO space for serial debugging.
	 * This allows debug messages to be output
	 * via a serial console before paging_init.
	 */
	ldr	r3, [r8, #MACHINFO_PGOFFIO]
	add	r0, r4, r3
	rsb	r3, r3, #0x4000			@ PTRS_PER_PGD*sizeof(long)
	cmp	r3, #0x0800			@ limit to 512MB
	movhi	r3, #0x0800
	add	r6, r0, r3
	ldr	r3, [r8, #MACHINFO_PHYSIO]
	orr	r3, r3, r7
1:	str	r3, [r0], #4
	add	r3, r3, #1 << 20
	teq	r0, r6
	bne	1b
#if defined(CONFIG_ARCH_NETWINDER) || defined(CONFIG_ARCH_CATS)
	/*
	 * If we're using the NetWinder or CATS, we also need to map
	 * in the 16550-type serial port for the debug messages
	 */
	add	r0, r4, #0xff000000 >> 18
	orr	r3, r7, #0x7c000000
	str	r3, [r0]
#endif
#ifdef CONFIG_ARCH_RPC
	/*
	 * Map in screen at 0x02000000 & SCREEN2_BASE
	 * Similar reasons here - for debug.  This is
	 * only for Acorn RiscPC architectures.
	 */
	add	r0, r4, #0x02000000 >> 18
	orr	r3, r7, #0x02000000
	str	r3, [r0]
	add	r0, r4, #0xd8000000 >> 18
	str	r3, [r0]
#endif
#endif
	mov	pc, lr
	.ltorg

#include "head-common.S"